Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.6391. Min Act: -0.1700
Data Index: 869778 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.6478. Min Act: -0.1700
Data Index: 4108034 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.6304. Min Act: -0.1700
Data Index: 4744551 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.6042. Min Act: -0.1700
Data Index: 8220650 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.6304. Min Act: -0.1700
Data Index: 1178547 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5955. Min Act: -0.1700
Data Index: 4523953 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.6042. Min Act: -0.1700
Data Index: 2260925 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5955. Min Act: -0.1700
Data Index: 1911382 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5867. Min Act: -0.1700
Data Index: 8479916 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5955. Min Act: -0.1700
Data Index: 1203701 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5867. Min Act: -0.1700
Data Index: 6369532 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5867. Min Act: -0.1700
Data Index: 6628181 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5867. Min Act: -0.1700
Data Index: 7329129 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5780. Min Act: -0.1700
Data Index: 8383493 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5780. Min Act: -0.1700
Data Index: 5163821 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5692. Min Act: -0.1700
Data Index: 2295230 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5780. Min Act: -0.1700
Data Index: 8264 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5692. Min Act: -0.1700
Data Index: 5647497 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5692. Min Act: -0.1698
Data Index: 8127524 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6478. Min Range: -1.6478
Max Act: 1.5605. Min Act: -0.1700
Data Index: 7269836 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19